# docs.jina.ai: agentic web grade C

Score 23 (coverage 20 + breadth 3 + conformance 0); 3 standards observed across 2 of 9 steps; checked 2026-10-26T09:29:20Z. This grades the agent-facing files published at docs.jina.ai, not the organisation's products.

## Manifests

| Manifest | Path | Result | Errors | Warnings |
| --- | --- | --- | --- | --- |
| Agentic Resource Discovery | /.well-known/ard.json | errors | body is not valid JSON |  |
| AI Catalog well-known file | /.well-known/ai-catalog.json | errors | body is not valid JSON |  |
| MCP Server Cards (SEP-2127) | /mcp/server-card | errors | body is not valid JSON |  |
| Agent2Agent Protocol | /.well-known/agent-card.json | errors | body is not valid JSON |  |
| llms.txt | /llms.txt | valid |  | the H1 is not the first line; no blockquote summary under the title; no Markdown links: list the pages an agent should read |
| AGENTS.md | /AGENTS.md | valid |  |  |
| Agent Skills | /.well-known/agent-skills/index.json | errors | body is not valid JSON |  |
| api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs | /.well-known/api-catalog | errors | body is not valid JSON |  |
| AI Crawler User-Agent Tokens in robots.txt | /robots.txt | errors | no User-agent group at all | no AI crawler token named (GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, ...); the policy for them is whatever User-agent: * says (unspecified); no Sitemap: line; no Agentmap: line (optional convention pointing agents at /.well-known/ard.json); no Content-Signal: line (optional; states ai-train / search / ai-input preferences) |
| security.txt (RFC 9116) | /.well-known/security.txt | errors | Contact: missing (RFC 9116 requires it); Expires: missing (RFC 9116 requires it) | Canonical: missing |
| auth.md | /auth.md | errors | none of the auth.md mechanism names found (identity_assertion, service_auth, anonymous) |  |
| Open Knowledge Format | /okf/index.md | errors | missing YAML frontmatter block (--- ... ---); missing okf_version (0.1 or 0.2) in frontmatter (OKF §8) | no Markdown links to concept .md files |

## Standards observed

- llms.txt: https://docs.jina.ai/llms.txt (https://agenticweb.wiki/protocols/llms-txt/)
- AGENTS.md: https://docs.jina.ai/AGENTS.md (https://agenticweb.wiki/protocols/agents-md/)
- agents.txt: https://docs.jina.ai/agents.txt (https://agenticweb.wiki/protocols/agents-txt/)

## Cheapest next steps


Published a manifest or spotted a path we missed? Submit at https://agenticweb.wiki/submit/ or email mailto:info@belgravialabs.com?subject=Manifest%20or%20correction%20for%20docs.jina.ai.

## Agent pre-flight & practical readiness

Preferred mode: `llms_txt`. GET /llms.txt and follow the links it names. That index is the page list an agent should read.

Fetch: `GET https://docs.jina.ai/llms.txt` GET /llms.txt and follow its links.

Practical readability: exa_parsable yes, markdown negotiation no, render `ssr_rich`, HTML quality `high`.

AI crawler posture: `all_ai_blocked` · Assistant access: OpenAI `unspecified`, Anthropic `unspecified`, Google `unspecified`, Perplexity `unspecified`, Exa `unspecified`.

Readiness subscores: reach 0/20, readability 20/30, capabilities 4/35, conformance 0/15, total 24/100, grade D.

## Rubric

+10 per lifecycle step with a standard observed, counting manifests that validate or that the probe rule for the standard recognises (a valid MCP server card counts for MCP; max 90); +3 per observed standard beyond the first two (max 15); conformance +15 (+10 with one manifest) minus 5 per agent-facing manifest with errors, never below 0 (security.txt is reported, not scored). Lifecycle grade: A+ >= 60, A >= 45, B >= 30, C >= 20, D >= 10. Strict 100-point composite (subscores.total_100 / subscores.grade_100): reach_and_policy (20) + readability (30) + capabilities (35) + conformance (15), where A+ >= 80, A >= 65, B >= 45, C >= 28, D >= 15.

JSON: https://agenticweb.wiki/check/docs.jina.ai/index.json · badge: https://agenticweb.wiki/badge/docs.jina.ai.svg